no code implementations • 12 Jul 2023 • WeiQin Chuah, Ruwan Tennakoon, Reza Hoseinnezhad, David Suter, Alireza Bab-Hadiashar
This approach is invariant to both affine shifts and changes in energy within a local feature patch and eliminates the need for commonly used non-linear activation functions.
no code implementations • CVPR 2022 • WeiQin Chuah, Ruwan Tennakoon, Reza Hoseinnezhad, Alireza Bab-Hadiashar, David Suter
State-of-the-art stereo matching networks trained only on synthetic data often fail to generalize to more challenging real data domains.
no code implementations • 15 Jun 2021 • WeiQin Chuah, Ruwan Tennakoon, Alireza Bab-Hadiashar, David Suter
We provide evidence that demonstrates that learning of features in the synthetic domain by a stereo matching network is heavily influenced by two "shortcuts" presented in the synthetic data: (1) identical local statistics (RGB colour features) between matching pixels in the synthetic stereo images and (2) lack of realism in synthetic textures on 3D objects simulated in game engines.
no code implementations • 10 Sep 2020 • WeiQin Chuah, Ruwan Tennakoon, Reza Hoseinnezhad, Alireza Bab-Hadiashar, David Suter
Consequently, the learning algorithms often produce unreliable depth estimates of foreground objects, particularly at large distances~($>50$m).